{"id":"https://openalex.org/W4415538187","doi":"https://doi.org/10.1145/3746027.3762002","title":"LVLM-MIR: Large Vision-Language Model with Parameter-Efficient Fine-Tuning for Multimodal Interleaved Reasoning","display_name":"LVLM-MIR: Large Vision-Language Model with Parameter-Efficient Fine-Tuning for Multimodal Interleaved Reasoning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538187","doi":"https://doi.org/10.1145/3746027.3762002"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3197-8103","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032096290","display_name":"Xilong Lu","orcid":"https://orcid.org/0009-0002-4655-6517"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilong Lu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-4655-6517","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390483","display_name":"Cong Wang","orcid":"https://orcid.org/0000-0002-4539-2525"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Wang","raw_affiliation_strings":["Huawei 2012 Labs, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4539-2525","affiliations":[{"raw_affiliation_string":"Huawei 2012 Labs, Hefei, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007719477","display_name":"Qiang Ling","orcid":"https://orcid.org/0000-0001-5688-4130"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Ling","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5688-4130","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32709021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13806","last_page":"13812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5503000020980835},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5320000052452087},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5291000008583069},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4925999939441681},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4165000021457672},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.36809998750686646},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.3440000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976999878883362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5982999801635742},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5503000020980835},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34869998693466187},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2963177403","https://openalex.org/W2963184176","https://openalex.org/W2963524571","https://openalex.org/W3167051144","https://openalex.org/W4280589619","https://openalex.org/W4312910992","https://openalex.org/W4312956471","https://openalex.org/W4321605134","https://openalex.org/W4386066385","https://openalex.org/W4400125901","https://openalex.org/W4403713288"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"interleaved":[1,8],"reasoning,":[2],"which":[3],"requires":[4],"models":[5],"to":[6,52],"understand":[7],"image-text":[9],"sequences":[10],"and":[11,38,70,81,88,126,142,162],"multiple":[12],"images,":[13],"is":[14],"a":[15,24,61],"critical":[16],"challenge":[17],"in":[18,85,130,149,157],"contemporary":[19],"AI.":[20],"This":[21],"paper":[22],"proposes":[23],"parameter-efficient":[25],"fine-tuning":[26,82,139],"framework":[27,45],"based":[28],"on":[29],"Large":[30],"Vision-Language":[31],"Models,":[32],"with":[33,54,97,104],"Qwen2.5-VL":[34],"as":[35],"the":[36,109,131],"backbone":[37],"Low-Rank":[39],"Adaptation":[40],"for":[41],"task-specific":[42],"adaptation.":[43],"The":[44],"integrates":[46],"four":[47],"stages:":[48],"multimodal":[49,95],"input":[50],"preprocessing":[51],"align":[53],"pre-training":[55],"distributions,":[56],"visual":[57,87,141,151],"feature":[58,160],"extraction":[59],"via":[60,67,73],"modified":[62],"Vision":[63],"Transformer,":[64],"cross-modal":[65,164],"fusion":[66],"attention":[68],"mechanisms,":[69],"response":[71],"generation":[72],"an":[74,121],"autoregressive":[75],"decoder.":[76],"By":[77],"freezing":[78],"pre-trained":[79],"weights":[80],"low-rank":[83],"adapters":[84],"both":[86],"language":[89,143],"modules,":[90],"it":[91,115],"balances":[92],"preserving":[93],"general":[94],"knowledge":[96],"optimizing":[98],"target":[99],"tasks,":[100],"achieving":[101,120],"high":[102],"performance":[103],"low":[105],"computational":[106],"overhead.":[107],"On":[108],"MIRAGE":[110],"Challenge":[111],"Track":[112],"A":[113],"Dataset,":[114],"performs":[116],"strongly":[117],"across":[118],"subtasks,":[119],"aggregate":[122],"score":[123],"of":[124,140],"0.7857":[125],"securing":[127],"second":[128],"place":[129],"challenge.":[132],"Ablation":[133],"studies":[134],"confirm":[135],"that":[136],"joint":[137],"LoRA":[138],"modules":[144],"yields":[145],"optimal":[146],"results;":[147],"limitations":[148],"fine-grained":[150],"difference":[152],"tasks":[153],"indicate":[154],"future":[155],"directions":[156],"enhancing":[158],"subtle":[159],"capture":[161],"adaptive":[163],"alignment.":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}